© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83776
    Prev
    Next
    INDEX
    Explanations

    Taipei, utilizar, esta, Nesta

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly fires on proper‐noun tokens—especially place names (e.g. “Taipei”) and similar capitalized terms.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    O
    -2.83
    U
    -2.42
    K
    -2.09
    m
    -2.09
    <i>
    -2.00
     лишь
    -1.98
    che
    -1.97
    柃
    -1.95
     我们
    -1.91
    E
    -1.91
    POSITIVE LOGITS
    髕
    2.55
    ᨘ
    2.33
     obligado
    2.17
     italianos
    2.16
    慥
    2.08
    臯
    2.06
    襌
    2.05
    剮
    2.02
     ウォッチ
    2.00
    ––
    1.98
    Activations Density 0.001%

    No Known Activations